© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22502
    Prev
    Next
    INDEX
    Explanations

    here

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     though
    0.54
    Though
    0.45
    though
    0.42
     Though
    0.41
    {&
    0.40
     страницы
    0.39
     зае
    0.38
     Page
    0.38
     page
    0.37
     Pages
    0.37
    POSITIVE LOGITS
    ]]:
    0.40
     "¿
    0.38
     cir
    0.36
     bien
    0.35
     "????
    0.34
    )$\\
    0.34
    Съ
    0.34
     Shown
    0.34
    ടിക്ക
    0.34
    🎪
    0.34
    Activations Density 0.005%

    No Known Activations